Smart gas internet of things system for gas safety management

Abstract

Provided is a smart gas Internet of Things (IoT) system for gas safety management. The system includes a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas indoor device sensing network platform, and a smart gas indoor device object platform. The smart gas user platform is configured as a terminal device; the smart gas indoor device sensing network platform is configured as a plurality of groups of gateway servers or a plurality of groups of intelligent routers; the smart gas indoor device object platform includes a safety valve control device object sub-platform, the safety valve control device object sub-platform is configured as indoor gas devices and gas safety detection devices; and the smart gas safety management platform includes a smart gas indoor safety management sub-platform and a smart gas data center.

What is claimed is: 
     
         1 . A smart gas Internet of Things (IoT) system for gas safety management, wherein the system comprises a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas indoor device sensing network platform, and a smart gas indoor device object platform; wherein
 the smart gas user platform is configured as a terminal device, and is configured to interact with the smart gas service platform to send request information of a target user to the smart gas service platform, and receive analysis information of a gas abnormity cause uploaded by the smart gas service platform;   the smart gas service platform is configured to receive and transmit data and information, interact with the smart gas safety management platform to send the request information of the target user to the smart gas safety management platform, and receive the analysis information of the gas abnormity cause uploaded by the smart gas safety management platform;   the smart gas indoor device sensing network platform is configured as a plurality of groups of gateway servers or a plurality of groups of intelligent routers, and is configured to receive information related to gas abnormity uploaded by the smart gas indoor device object platform and upload the information related to gas abnormity to the smart gas safety management platform;   the smart gas indoor device object platform includes a safety valve control device object sub-platform, the safety valve control device object sub-platform is configured as indoor gas devices and gas safety detection devices, and is configured to obtain the information related to gas abnormity, upload the information related to gas abnormity to the smart gas indoor device sensing network platform, and receive an instruction for obtaining the information related to gas abnormity issued by the smart gas indoor device sensing network platform; and   the smart gas safety management platform includes a smart gas indoor safety management sub-platform and a smart gas data center, and the smart gas indoor safety management sub-platform interacts with the smart gas data center in two directions; and   the smart gas data center is configured to:   receive the request information input by the target user from the smart gas user platform based on the smart gas service platform, wherein the request information includes a request of the target user for analyzing the gas abnormity cause;   the smart gas indoor safety management sub-platform is configured to:   extract user data based on the request information, wherein the user data includes at least one of positioning information of the target user, a gas use type of the target user, and gas meter number information of the target user;   extract, through the smart gas indoor device sensing network platform, gas data based on the user data extracted by the smart gas indoor device object platform, wherein the gas data includes a gas balance, gas pipeline data involved by the target user, gas usage data, and gas abnormity data of the target user;   in response to the gas data exceeding a safety threshold, automatically alarm and automatically push alarm information to the smart gas user platform;   determine pipeline information and user terminal information based on the user data and the gas data, wherein the pipeline information includes pipeline gas information and pipeline terminal information;   construct, based on the pipeline information and the user terminal information, an image, wherein a node of the image includes a pipeline terminal node and a user terminal node, an edge of the image includes a gas pipeline between nodes, and a direction of the edge is a gas delivery direction; attribute of the pipeline terminal node includes an abnormity score, gas use data, and gas abnormity data of the pipeline terminal node; attribute of the user terminal node includes an abnormity score, gas usage data, user image data, and gas abnormity data of the user terminal node; and attribute of the edge includes a weight value and gas flow information;   analyze, based on a preset algorithm, the image to determine the analysis information of the gas abnormity cause, wherein the analysis information of the gas abnormity cause includes an abnormity score of the node;   send the analysis information of the gas abnormity cause to the smart gas data center, to cause that the smart gas data center sends the analysis information of the gas abnormity cause to the smart gas user platform through the smart gas service platform; and   in response to the abnormity score exceeding a preset safety threshold, automatically generate a control signal, and send the control signal to the safety valve control device object sub-platform to close a gas supply valve.   
     
     
         2 . The system of  claim 1 , wherein the analysis information of the gas abnormity cause further includes a type of the gas abnormity cause and an occurrence probability of each type of the gas abnormity cause, wherein the type of the gas abnormity cause includes an insufficient balance of gas fee, gas pipeline blockage, terminal failure, or gas leakage;
 the smart gas indoor device object platform further includes a safety monitoring device object sub-platform, wherein the smart gas indoor safety management sub-platform is further configured to:
 predict the type of the gas abnormity cause and the occurrence probability of each type of the gas abnormity based on attribute of a current node, attribute of an adjacent node, and attribute of an adjacent edge through a prediction model, wherein the attribute of the current node and the attribute of the adjacent node include an updated abnormity score of the current node and an updated abnormity score of the adjacent node, the prediction model is a machine learning model, and the prediction model includes a multi-type model; and 
 in response to the type of the gas abnormity cause being the gas leakage, control, by the safety monitoring device object sub-platform, a gas concentration detection device to detect whether there is the gas leakage, and automatically push the alarm information to the smart gas user platform. 
   
     
     
         3 . The system of  claim 2 , wherein the smart gas indoor safety management sub-platform is further configured to:
 obtain a plurality of training samples; and   obtain the prediction model by training an initial prediction model based on the plurality of training samples and labels corresponding to plurality of training samples, wherein each of the plurality of training samples includes a plurality of sample node attribute and a plurality of sample edge attribute, a label of the training sample includes the type of gas abnormity cause and the occurrence probability of each type of the gas abnormity cause corresponding to the training sample; and the plurality of training samples and the labels are obtained based on historical data; wherein the training includes:
 inputting the training samples to the initial prediction model, 
 constructing a loss function based on outputs of the initial prediction model and the labels, 
 updating a parameter of the initial prediction model through the loss function until a trained initial prediction model satisfies a preset condition; and 
 obtaining the prediction model, wherein the preset condition includes that the loss function is smaller than a threshold, the loss function converges, or a training period reaches a threshold. 
   
     
     
         4 . The system of  claim 1 , wherein the smart gas indoor safety management sub-platform is further configured to:
 update, through a plurality of rounds of iterations, the abnormity score of the node, and stop the iterations until the abnormity score satisfies a second preset condition, wherein the second preset condition includes at least one of a function convergence, an abnormity score of a node reaching the preset safety threshold, and a number of the iterations reaching a threshold.   
     
     
         5 . The system of  claim 4 , wherein the smart gas indoor safety management sub-platform is further configured to:
 in each round of iteration, for each node,   determine an updated abnormity score of the node based on an abnormity score of a node to be updated in a current round of iteration, abnormity scores of other nodes directly connected to the node to be updated, and weight values of edges between the node and other connected nodes; and   take the updated abnormity score of the node as an abnormity score of the node to be updated in a next round of iteration, wherein in a first round of iteration, the abnormity score of the node to be updated is an initial abnormity score of the node, and the initial abnormity score of the node is determined based on the gas usage data and the gas abnormity data of the node.   
     
     
         6 . The system of  claim 5 , wherein the smart gas indoor safety management sub-platform is further configured to:
 update an abnormity score of an ith node in a jth round of iteration based on an algorithm as follows:   
       
         
           
             
               
                 
                   V 
                   i 
                 
                 ′ 
               
               = 
               
                 
                   p 
                   * 
                   
                     V 
                     i 
                   
                 
                 + 
                 
                   q 
                   * 
                   
                     
                       ∑ 
                       
                         k 
                         = 
                         1 
                       
                       K 
                     
                       
                     
                       ( 
                       
                         
                           V 
                           k 
                         
                         * 
                         
                           R 
                           ki 
                         
                       
                       ) 
                     
                   
                 
               
             
           
         
         where 
       
       
         
           
             
               V 
               i 
               ′ 
             
           
         
          denotes the updated abnormality score of the node, which is the abnormity score to be updated in the next round of iteration; V i  and V k  denote an abnormity score of the ith node to be updated and an abnormity score of a kth node to be updated in the current round of iteration; p and q are weight coefficients, which are determined by the smart gas safety management platform according to attribute of the nodes and the edges in the image; k denotes a node that has an edge connection with the ith node, and K denotes a number of nodes that have an edge connection with the ith node; and R ki  denotes a weight value of an edge between the ith node and the kth node. 
       
     
     
         7 . The system of  claim 1 , wherein the smart gas indoor safety management sub-platform is further configured to:
 when attribute of a plurality of same-level nodes includes current abnormity data, increase an abnormity score of a common parent node of the plurality of same-level nodes, wherein the same-level nodes refer to nodes that share a same common parent node, and the common parent node is a parent node with edges directly connected with the plurality of same-level nodes respectively.   
     
     
         8 . The system of  claim 1 , wherein the smart gas indoor safety management sub-platform is further configured to:
 extract a preset rule based on a rule base, and determine a candidate gas abnormity cause and a certainty level of the candidate gas abnormity cause through a rule determination engine; wherein
 the rule base refers to a knowledge base composed of various preset rules; 
 the preset rule refers to a rule that is artificially set in advance and is used to determine whether the user data and the gas data satisfy a condition, and the preset rule includes thresholds related to determining the type of the gas abnormity cause and the certainty level; 
 the certainty level refers to a level of certainty of the gas abnormity cause, which is expressed as a percentage or a grade; the certainty level of 100% indicates that the gas abnormity cause is directly determined; the certainty level being less than 100% indicates that the gas abnormity cause is concluded through data analysis; and 
 the preset rule or the rule determination engine is used to determine whether the user data and the gas data satisfy the preset rule. 
   
     
     
         9 . The system of  claim 8 , wherein the smart gas indoor safety management sub-platform is further configured to:
 determine whether the certainty level satisfies a first preset condition, wherein the first preset condition refers to a condition set in advance for determining whether to need to further obtain other data to continue to analyze the gas abnormity cause, and the first preset condition includes the certainty level being greater than or equal to 90% or the certainty level being greater than or equal to level IV; and   in response to a determination that the certainty level does not satisfy the first preset condition, determine, based on the pipeline information and the user terminal information, the analysis information of the gas abnormity cause through a preset algorithm.